Search NASA⌕ Search

SEARCH · Search NASA

Results for “FORECASTS”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13

Impacts of the Eruption of Mount Pinatubo on Surface Temperatures and Precipitation Forecasts With the NASA GEOS Subseasonal-to-Seasonal System

A contemporary seasonal forecasting system is used to study the impacts of a volcanic sulfate injection into the stratosphere on the seasonal forecasts for surface temperatures, the El Niño Southern Oscillation (ENSO), and precipitation. The focus is a case study of the June 1991 eruption of Mt. Pinatubo, Philippines and the period from July 1991 to February 1992. Version 2 of the Goddard Earth Observing System (GEOS) subseasonal-to-seasonal (S2S) forecasting system is used in this study. GEOS-S2S includes the GOddard Chemistry, Aerosols, Radiation and Transport (GOCART) aerosol module, which allows to prognostically simulate aerosol distributions. GOCART is coupled to the radiation and cloud modules to include the impact of the eruption on forecasted radiation and precipitation. The coupled GEOS-S2S system was initialized in May 1991 with fields based on observations to produce ten-member 9-month forecasts with and without the volcanic sulfur injection. The results of these ensemble experiments demonstrate that including Mt. Pinatubo in seasonal forecasts would improve the forecasts of the 1991–1992 global mean temperature and precipitation but worsen the forecast of ENSO by strengthening of El Niño beyond what showed in observations. Most significant changes in the forecasts of temperatures and precipitation are limited to the tropics. The only land area where the inclusion of Pinatubo significantly lowered the forecasted precipitation is tropical Africa.

Mt. Pinatubo↗

Investigating the potential of a global precipitation forecast to inform landslide prediction

Extreme rainfall events within landslide-prone areas can be catastrophic, resulting in loss of property, infrastructure, and life. A global Landslide Hazard Assessment for Situational Awareness (LHASA) model provides routine near-real time estimates of landslide hazard using Integrated Multi-Satellite Precipitation Retrievals for the Global Precipitation Mission (IMERG). However, it does not provide information on potential landslide hazard in the future. Forecasting potential landslide events at a global scale presents an area of open research. This study compares a global precipitation forecast provided by NASA's Goddard Earth Observing System (GEOS) with near-real time satellite precipitation estimates. The Multi-Radar Multi-Sensor gauge corrected (MRMS-GC) reference is used to assess the performance of both satellite and model-based precipitation products over the contiguous United States (CONUS). The forecast lead time of 24hrs is considered, with a focus on extreme precipitation events. The performance of IMERG and GEOS-Forecast products is assessed in terms of the probability of detection, success ratio, critical success index and hit bias as well as continuous statistics. The results show that seasonality influences the performance of both satellite and model-based precipitation products. Comparison of IMERG and GEOS-Forecast globally as well as in several event case studies (Colombia, southeast Asia, and Tajikistan) reveals that GEOS-Forecast detects extreme rainfall more frequently relative to IMERG for these specific analyses. For recent landslide points across the globe, the 24hr accumulated precipitation forecast >100 mm corresponds well with near-real time daily accumulated IMERG precipitation estimates. GEOS-Forecast and IMERG precipitation match more closely for tropical cyclones than for other types of storms. The main intention of this study is to assess the viability of using a global forecast for landslide predictions and understand the extent of the variability between these products to inform where we would expect the landslide modeling results to most prominently diverge. Results of this study will be used to inform how forecasted precipitation estimates can be incorporated into the LHASA model to provide the first global predictive view of landslide hazards.

S. Khan↗

Investigating the Potential of A Global Precipitation Forecast to Inform Landslide Prediction

Extreme rainfall events within landslide-prone areas can be catastrophic, resulting in loss of property, infra-structure, and life. A global Landslide Hazard Assessment for Situational Awareness (LHASA) model provides routine near-real time estimates of landslide hazard using Integrated Multi-Satellite Precipitation Retrievals for the Global Precipitation Mission (IMERG). However, it does not provide information on potential landslide hazard in the future. Forecasting potential landslide events at a global scale presents an area of open research. This study compares a global precipitation forecast provided by NASA’s Goddard Earth Observing System (GEOS) with near-real time satellite precipitation estimates. The Multi-Radar Multi-Sensor gauge corrected (MRMS-GC) reference is used to assess the performance of both satellite and model-based precipitation products over the contiguous United States (CONUS). The forecast lead time of 24hrs is considered, with a focus on extreme precipitation events. The performance of IMERG and GEOS-Forecast products is assessed in terms of the probability of detection, success ratio, critical success index and hit bias as well as continuous statistics. The results show that seasonality influences the performance of both satellite and model-based precipitation products. Comparison of IMERG and GEOS-Forecast globally as well as in several event case studies (Colombia, southeast Asia, and Tajikistan) reveals that GEOS-Forecast detects extreme rainfall more frequently relative to IMERG for these specific analyses. For recent landslide points across the globe, the 24hr accumulated precipitation forecast >100 mm corresponds well with near-real time daily accumulated IMERG precipitation estimates. GEOS-Forecast and IMERG precipitation match more closely for tropical cyclones than for other types of storms. The main intention of this study is to assess the viability of using a global forecast for landslide predictions and understand the extent of the variability between these products to inform where we would expect the landslide modeling results to most prominently diverge. Results of this study will be used to inform how forecasted precipitation estimates can be incorporated into the LHASA model to provide the first global predictive view of landslide hazards.

S. Khan↗

A Community Convention for Ecological Forecasting: Output Files and Metadata Version 1.0

This paper summarizes the open community conventions developed by the Ecological Forecasting Initiative (EFI) for the common formatting and archiving of ecological forecasts and the metadata associated with these forecasts. Such open standards are intended to promote interoperability and facilitate forecast communication, distribution, validation, and synthesis. For output files, we first describe the convention conceptually in terms of global attributes, forecast dimensions, forecasted variables, and ancillary indicator variables. We then illustrate the application of this convention to the two file formats that are currently preferred by the EFI, netCDF (network common data form), and comma-separated values (CSV), but note that the convention is extensible to future formats. For metadata, EFI's convention identifies a subset of conventional metadata variables that are required (e.g., temporal resolution and output variables) but focuses on developing a framework for storing information about forecast uncertainty propagation, data assimilation, and model complexity, which aims to facilitate cross-forecast synthesis. The initial application of this convention expands upon the Ecological Metadata Language (EML), a commonly used metadata standard in ecology. To facilitate community adoption, we also provide a Github repository containing a metadata validator tool and several vignettes in R and Python on how to both write and read in the EFI standard. Lastly, we provide guidance on forecast archiving, making an important distinction between short-term dissemination and long-term forecast archiving, while also touching on the archiving of code and workflows. Overall, the EFI convention is a living document that can continue to evolve over time through an open community process.

Michael C. Dietze↗

Evaluating precipitation, streamflow, and inundation forecasting skills during extreme weather events: A case study for an urban watershed

Integrated forecasting systems for precipitation, streamflow, and floodplain inundation are of critical importance in mitigating the impacts of destructive floods caused by extreme weather events. However, the skills of streamflow and floodplain inundation forecasts derived from various Quantitative Precipitation Forecasts (QPF) require a greater level of understanding. In this paper, a set of QPF developed by the National Weather Service (NWS) were used to drive a flood modeling system obtained utilizing offline coupling of a physics-based distributed hydrological model, the Distributed Hydrology Soil and Vegetation Model (DHSVM), and a hydrodynamic model, the Two-dimensional Runoff Inundation Toolkit for Operational Needs (TRITON). This flood modeling system was used to produce forecasts of streamflow and floodplain inundation maps during three major flood events in the Brays Bayou Watershed (Houston, Texas, USA) for a range of QPF durations (6–72 h). Then, to investigate the effects of increasing QPF durations on the forecasts, the forecasting skills of precipitation, streamflow, and floodplain inundation were quantified. The results show that: 1) QPF skills for more intense and sustained events such as hurricanes and tropical storms are higher than for shorter, less intense events; 2) while QPF and streamflow forecasting skills decrease as QPF durations increase, inundation forecasts under longer QPF durations (24 or 72 h) show higher skills; 3) extending the maximum QPF duration in operational hydrologic modeling from 24 h (under normal circumstances) to 72 h (for extreme events) may increase the skills of long lead time forecasts for large-scale events like Hurricane Harvey.

54 ENVIRONMENTAL SCIENCES↗

Evaluation of Wind Power Forecasts from the Vermont Weather Analytics Center and Identification of Improvements

The goal of this analysis was to assess the wind power forecast accuracy of the Vermont Weather Analytics Center (VTWAC) forecast system and to identify potential improvements to the forecasts. Based on the analysis at Georgia Mountain, the following recommendations for improving forecast performance were made: 1. Resolve the significant negative forecast bias in February-March 2017 (50% underprediction on average) 2. Improve the ability of the forecast model to capture the strong diurnal cycle of wind power 3. Add ability for forecast model to assess internal wake loss, particularly at sites where strong diurnal shifts in wind direction are present. Data availability and quality limited the robustness of this forecast assessment. A more thorough analysis would be possible given a longer period of record for the data (at least one full year), detailed supervisory control and data acquisition data for each wind plant, and more detailed information on the forecast system input data and methodologies.

17 WIND ENERGY↗

Coupling computational fluid dynamics with the high resolution rapid refresh model for forecasting dynamic line ratings

This study looks at forecasted dynamic line ratings in southern Idaho by using data from the High Resolution Rapid Refresh (HRRR) model for forecasted weather conditions. The HRRR model can provide accurate 18- hour forecasts with a 15-minute temporal resolution. Typical static ratings used for over head transmission lines use overly conservative assumptions for local weather conditions, such as using the maximum solar irradiance or temperature measured during the summer combined with low wind speed for an entire season. The HRRR forecast model used here has a high spatial resolution to provide local forecast conditions along the entire length of a transmission line. The area that is of interest in this study is in southern Idaho spanning a total of 15,000 square kilometers. The forecasted weather data is coupled with a computational fluid dynamics model of the wind in the region to improve the resolution to an even finer scale for resolving local convective cooling rates on each individual transmission line midpoint span. This high fidelity approach can be used to find the minimum ampacity limit across all given midpoints of a transmission line to determine the absolute minimum to be used for the line rating. The ability to increase the line rating above the conservative static approach with the forecasted weather data provides a large potential to alleviate congestion and provide data for the utility market transactions. Furthermore, this study shows that for the region of interest, using forecasted weather data coupled with CFD modeling will calculate DLR ampacity rating above static about 90% of the time, with only a small relative error in the forecasted ampacity over time.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Probabilistic Wind Power Ramp Forecasting Based on a Scenario Generation Method

Wind power ramps (WPRs) are particularly important in the management and dispatch of wind power and currently drawing the attention of balancing authorities. With the aim to reduce the impact of WPRs for power system operations, this paper develops a probabilistic ramp forecasting method based on a large number of simulated scenarios. An ensemble machine learning technique is first adopted to forecast the basic wind power forecasting scenario and calculate the historical forecasting errors. A continuous Gaussian mixture model (GMM) is used to fit the probability distribution function (PDF) of forecasting errors. The cumulative distribution function (CDF) is analytically deduced. The inverse transform method based on Monte Carlo sampling and the CDF is used to generate a massive number of forecasting error scenarios. An optimized swinging door algorithm is adopted to extract all the WPRs from the complete set of wind power forecasting scenarios. The probabilistic forecasting results of ramp duration and start-time are generated based on all scenarios. Numerical simulations on publicly available wind power data show that within a predefined tolerance level, the developed probabilistic wind power ramp forecasting method is able to predict WPRs with a high level of sharpness and accuracy.

17 WIND ENERGY↗

Probabilistic Short-Term Wind Forecasting Based on Pinball Loss Optimization

Probabilistic wind power forecasts that quantify the uncertainty in wind output have the potential to aid in the economic grid integration of wind power at large penetration levels. In this paper, a novel probabilistic wind forecasting approach based on pinball loss optimization is proposed, in conjunction with a multi-model machine learning based ensemble deterministic forecasting framework. By assuming the point-forecasted value as the mean at each point, one unknown parameter (i.e., standard deviation) of a predictive distribution at each forecasting point is determined by minimizing the pinball loss. A surrogate model is developed to represent the unknown distribution parameter as a function of deterministic forecasts. This surrogate model can be used together with deterministic forecasts to predict the unknown distribution parameter and thereby generate probabilistic forecasts. Numerical results of case studies show that the proposed method has improved the pinball loss by up to 35% compared to a baseline quantile regression forecasting model.

17 WIND ENERGY↗

Robust Deep Gaussian Process-Based Probabilistic Electrical Load Forecasting Against Anomalous Events

The abnormal events, such as the unprecedented COVID-19 pandemic, can significantly change the load behaviors, leading to huge challenges for traditional short-term forecasting methods. This article proposes a robust deep Gaussian processes (DGP)-based probabilistic load forecasting method using a limited number of data. Since the proposed method only requires a limited number of training samples for load forecasting, it allows us to deal with extreme scenarios that cause short-term load behavior changes. In particular, the load forecasting at the beginning of abnormal event is cast as a regression problem with limited training samples and solved by double stochastic variational inference DGP. The mobility data are also utilized to deal with the uncertainties and pattern changes and enhance the flexibility of the forecasting model. The proposed method can quantify the uncertainties of load forecasting outcomes, which would be essential under uncertain inputs. Extensive comparison results with other state-of-the-art point and probabilistic forecasting methods show that our proposed approach can achieve high forecasting accuracies with only a limited number of data while maintaining the excellent performance of capturing the forecasting uncertainties.

anomalous events↗

Day-Ahead Probabilistic Forecasting of Net-Load and Demand Response Potentials with High Penetration of Behind-the-Meter Solar-plus-Storage

The goal of this project is to develop advanced methods for day-ahead net-load forecasting, by leveraging the state-of-the-art machine learning techniques. The developed models produce both point and probabilistic forecasts for a variety of use cases, and are versatile to work with different types of data sets. The innovation lies in the novel design of the architectures, leveraging the most recent advances in machine learning that have not been explored in power systems, accompanied by techniques in the broader artificial intelligence fields such as fuzzy systems. This project has achieved the following accomplishments: (1) preprocessing of over 10 data sets covering varying geographical regions, time horizons, and system levels, which form a robust foundation for training and evaluating forecasting models across a wide range of realistic grid scenarios; (2) development of an interactive web app that enables exploratory analysis of load and generation data, and supports better understanding of data trends, anomalies, and correlations, facilitating model development and stakeholder engagement; (3) implementation of over 10 benchmark models for point and probabilistic forecasting, which include a mix of conventional machine learning methods and state-of-the-art deep learning approaches, providing a comprehensive baseline for performance comparison and validation of the proposed models; (4) development of a fuzzy system based gradient boosting model, tailored for small (less than 3 years) data sets, which achieves a mean absolute percentage error (MAPE) of 4% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (5) development of a Transformer (a state-of-the-art deep learning architecture) based neural network model, tailored for large (3 years or more) data sets, which achieves a MAPE of 2% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (6) development of a methodology for quantifying DR potential, and extensions of the previous models for multi-target forecasting of net load and DR potential, which achieve a MAPE of 10% for DR potential.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Wind Energy Management System EMS Integration Project: Incorporating Wind Generation and Load Forecast Uncertainties into Power Grid Operations

The power system balancing process, which includes the scheduling, real time dispatch (load following) and regulation processes, is traditionally based on deterministic models. Since the conventional generation needs time to be committed and dispatched to a desired megawatt level, the scheduling and load following processes use load and wind and solar power production forecasts to achieve future balance between the conventional generation and energy storage on the one side, and system load, intermittent resources (such as wind and solar generation), and scheduled interchange on the other side. Although in real life the forecasting procedures imply some uncertainty around the load and wind/solar forecasts (caused by forecast errors), only their mean values are actually used in the generation dispatch and commitment procedures. Since the actual load and intermittent generation can deviate from their forecasts, it becomes increasingly unclear (especially, with the increasing penetration of renewable resources) whether the system would be actually able to meet the conventional generation requirements within the look-ahead horizon, what the additional balancing efforts would be needed as we get closer to the real time, and what additional costs would be incurred by those needs. To improve the system control performance characteristics, maintain system reliability, and minimize expenses related to the system balancing functions, it becomes necessary to incorporate the predicted uncertainty ranges into the scheduling, load following, and, in some extent, into the regulation processes. It is also important to address the uncertainty problem comprehensively by including all sources of uncertainty (load, intermittent generation, generators’ forced outages, etc.) into consideration. All aspects of uncertainty such as the imbalance size (which is the same as capacity needed to mitigate the imbalance) and generation ramping requirement must be taken into account. The latter unique features make this work a significant step forward toward the objective of incorporating of wind, solar, load, and other uncertainties into power system operations. Currently, uncertainties associated with wind and load forecasts, as well as uncertainties associated with random generator outages and unexpected disconnection of supply lines, are not taken into account in power grid operation. Thus, operators have little means to weigh the likelihood and magnitude of upcoming events of power imbalance. In this project, funded by the U.S. Department of Energy (DOE), a framework has been developed for incorporating uncertainties associated with wind and load forecast errors, unpredicted ramps, and forced generation disconnections into the energy management system (EMS) as well as generation dispatch and commitment applications. A new approach to evaluate the uncertainty ranges for the required generation performance envelope including balancing capacity, ramping capability, and ramp duration has been proposed. The approach includes three stages: forecast and actual data acquisition, statistical analysis of retrospective information, and prediction of future grid balancing requirements for specified time horizons and confidence levels. Assessment of the capacity and ramping requirements is performed using a specially developed probabilistic algorithm based on a histogram analysis, incorporating all sources of uncertainties of both continuous (wind and load forecast errors) and discrete (forced generator outages and start-up failures) nature. A new method called the “flying brick” technique has been developed to evaluate the look-ahead required generation performance envelope for the worst case scenario within a user-specified confidence level. A self-validation algorithm has been developed to validate the accuracy of the confidence intervals.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Wind Energy Management System Integration Project Incorporating Wind Generation and Load Forecast Uncertainties into Power Grid Operations

The power system balancing process, which includes the scheduling, real time dispatch (load following) and regulation processes, is traditionally based on deterministic models. Since the conventional generation needs time to be committed and dispatched to a desired megawatt level, the scheduling and load following processes use load and wind power production forecasts to achieve future balance between the conventional generation and energy storage on the one side, and system load, intermittent resources (such as wind and solar generation) and scheduled interchange on the other side. Although in real life the forecasting procedures imply some uncertainty around the load and wind forecasts (caused by forecast errors), only their mean values are actually used in the generation dispatch and commitment procedures. Since the actual load and intermittent generation can deviate from their forecasts, it becomes increasingly unclear (especially, with the increasing penetration of renewable resources) whether the system would be actually able to meet the conventional generation requirements within the look-ahead horizon, what the additional balancing efforts would be needed as we get closer to the real time, and what additional costs would be incurred by those needs. In order to improve the system control performance characteristics, maintain system reliability, and minimize expenses related to the system balancing functions, it becomes necessary to incorporate the predicted uncertainty ranges into the scheduling, load following, and, in some extent, into the regulation processes. It is also important to address the uncertainty problem comprehensively, by including all sources of uncertainty (load, intermittent generation, generators’ forced outages, etc.) into consideration. All aspects of uncertainty such as the imbalance size (which is the same as capacity needed to mitigate the imbalance) and generation ramping requirement must be taken into account. The latter unique features make this work a significant step forward toward the objective of incorporating of wind, solar, load, and other uncertainties into power system operations. In this report, a new methodology to predict the uncertainty ranges for the required balancing capacity, ramping capability and ramp duration is presented. Uncertainties created by system load forecast errors, wind and solar forecast errors, generation forced outages are taken into account. The uncertainty ranges are evaluated for different confidence levels of having the actual generation requirements within the corresponding limits. The methodology helps to identify system balancing reserve requirement based on a desired system performance levels, identify system “breaking points”, where the generation system becomes unable to follow the generation requirement curve with the user-specified probability level, and determine the time remaining to these potential events. The approach includes three stages: statistical and actual data acquisition, statistical analysis of retrospective information, and prediction of future grid balancing requirements for specified time horizons and confidence intervals. Assessment of the capacity and ramping requirements is performed using a specially developed probabilistic algorithm based on a histogram analysis incorporating all sources of uncertainty and parameters of a continuous (wind forecast and load forecast errors) and discrete (forced generator outages and failures to start up) nature. Preliminary simulations using California Independent System Operator (California ISO) real life data have shown the effectiveness of the proposed approach. A tool developed based on the new methodology described in this report will be integrated with the California ISO systems. Contractual work is currently in place to integrate the tool with the AREVA EMS system.

17 WIND ENERGY↗

Advancing Data Assimilation in Operational Hydrologic Forecasting: Progresses, Challenges, and Emerging Opportunities

Data assimilation (DA) holds considerable potential for improving hydrologic predictions as demonstrated in numerous research studies. However, advances in hydrologic DA research have not been adequately or timely implemented in operational forecast systems to improve the skill of forecasts for better informed real-world decision making. This is due in part to a lack of mechanisms to properly quantify the uncertainty in observations and forecast models in real-time forecasting situations and to conduct the merging of data and models in a way that is adequately efficient and transparent to operational forecasters. The need for effective DA of useful hydrologic data into the forecast process has become increasingly recognized in recent years. This motivated a hydrologic DA workshop in Delft, the Netherlands in November 2010, which focused on advancing DA in operational hydrologic forecasting and water resources management. As an outcome of the workshop, this paper reviews, in relevant detail, the current status of DA applications in both hydrologic research and operational practices, and discusses the existing or potential hurdles and challenges in transitioning hydrologic DA research into cost-effective operational forecasting tools, as well as the potential pathways and newly emerging opportunities for overcoming these challenges. Several related aspects are discussed, including (1) theoretical or mathematical aspects in DA algorithms, (2) the estimation of different types of uncertainty, (3) new observations and their objective use in hydrologic DA, (4) the use of DA for real-time control of water resources systems, and (5) the development of community-based, generic DA tools for hydrologic applications. It is recommended that cost-effective transition of hydrologic DA from research to operations should be helped by developing community-based, generic modeling and DA tools or frameworks, and through fostering collaborative efforts among hydrologic modellers, DA developers, and operational forecasters.

forecasting↗

Ensemble Solar Forecasting Statistical Quantification and Sensitivity Analysis: Preprint

Uncertainties associated with solar forecasts present challenges to maintain grid reliability, especially at high solar penetrations. This study aims to quantify the errors associated with the day-ahead solar forecast parameters and the theoretical solar power output for a 51-kW solar power plant in a utility area in the state of Vermont, U.S. Forecasts were generated by three numerical weather prediction (NWP) models, including the Rapid Refresh, the High Resolution Rapid Refresh, and the North American Model, and a machine-learning ensemble model. A photovoltaic (PV) performance model was adopted to calculate theoretical solar power generation using the forecast parameters (e.g., irradiance, cell temperature, and wind speed). Errors of the power outputs were quantified using statistical moments and a suite of metrics, such as the normalized root mean squared error (NRMSE). In addition, the PV model's sensitivity to different forecast parameters was quantified and analyzed. Results showed that the ensemble model yielded forecasts in all parameters with the smallest NRMSE. The NRMSE of solar irradiance forecasts of the ensemble NWP model was reduced by 28.10% compared to the best of the three NWP models. Further, the sensitivity analysis indicated that the errors of the forecasted cell temperature attributed only approximately 0.12% to the NRMSE of the power output as opposed to 7.44% from the forecasted solar irradiance.

14 SOLAR ENERGY↗

Ensemble Solar Forecasting Statistical Quantification and Sensitivity Analysis

Uncertainties associated with solar forecasts present challenges to maintain grid reliability, especially at high solar penetrations. This study aims to quantify the errors associated with the day-ahead solar forecast parameters and the theoretical solar power output for a 51-kW solar power plant in a utility area in the state of Vermont, U.S. Forecasts were generated by three numerical weather prediction (NWP) models, including the Rapid Refresh, the High Resolution Rapid Refresh, and the North American Model, and a machine-learning ensemble model. A photovoltaic (PV) performance model was adopted to calculate theoretical solar power generation using the forecast parameters (e.g., irradiance, cell temperature, and wind speed). Errors of the power outputs were quantified using statistical moments and a suite of metrics, such as the normalized root mean squared error (NRMSE). In addition, the PV model's sensitivity to different forecast parameters was quantified and analyzed. Results showed that the ensemble model yielded forecasts in all parameters with the smallest NRMSE. The NRMSE of solar irradiance forecasts of the ensemble NWP model was reduced by 28.10% compared to the best of the three NWP models. Further, the sensitivity analysis indicated that the errors of the forecasted cell temperature attributed only approximately 0.12% to the NRMSE of the power output as opposed to 7.44% from the forecasted solar irradiance.

14 SOLAR ENERGY↗

Probabilistic Wind Power Ramp Forecasting Based on a Scenario Generation Method: Preprint

Wind power ramps (WPRs) are particularly important in the management and dispatch of wind power, and they are currently drawing the attention of balancing authorities. With the aim to reduce the impact of WPRs for power system operations, this paper develops a probabilistic ramp forecasting method based on a large number of simulated scenarios. An ensemble machine learning technique is first adopted to forecast the basic wind power forecasting scenario and calculate the historical forecasting errors. A continuous Gaussian mixture model (GMM) is used to fit the probability distribution function (PDF) of forecasting errors. The cumulative distribution function (CDF) is analytically deduced. The inverse transform method based on Monte Carlo sampling and the CDF is used to generate a massive number of forecasting error scenarios. An optimized swinging door algorithm is adopted to extract all the WPRs from the complete set of wind power forecasting scenarios. The probabilistic forecasting results of ramp duration and start time are generated based on all scenarios. Numerical simulations on publicly available wind power data show that within a predefined tolerance level, the developed probabilistic wind power ramp forecasting method is able to predict WPRs with a high level of sharpness and accuracy.

17 WIND ENERGY↗

A cross-dimensional analysis of data-driven short-term load forecasting methods with large-scale smart meter data

Electricity load forecasting is essential to utility operation and power grid stability. A wide spectrum of data-driven methods, ranging from linear regression models to more recent deep learning models have been adopted to forecast electric load over the years. However, there still lacks a holistic evaluation of the applicability of conventional statistical and machine learning based algorithms with respect to different temporal and spatial scopes, computational requirements, and sensitivity of model-tuning. Enabled by a large-scale electricity load profile dataset of over 40,000 residential customers in a utility region, we conducted a cross-dimensional analysis of data-driven load forecasting methods. Three regression-based and seven deep learning algorithms with different model configurations were evaluated in terms of their overall and peak load prediction accuracy, and training burdens, across spatial aggregation levels ranging from the transformer, feeder, substation, to neighborhood. We found, first, the load forecasting accuracy is constrained by a predictability boundary, influenced by the forecasting horizon and spatial aggregation level. Specifically, RandomForest, XGBoost, TFT, TSMixer, and TiDE models achieved less than 10 % prediction error for up to 96-h ahead forecasting for district, substation, and feeder levels, while other models struggle at long-horizon predictions; Second, for winter and summer peak load dates, most models were able to predict the peak demand timing within ± 1 h, but the prediction percentage error varied by models, with TFT and TiDE models being the top performers; Third, models with similar prediction accuracy can differ in training burden by an order of magnitude. Therefore, choosing model configurations that balance prediction performance and computational resource is an important practical consideration for large-scale deployment of the machine learning based load forecasting. The outcome of this study can guide researchers and practitioners to choose the proper load forecasting algorithms based on their problem scope, required accuracy, and available resources. The predictability boundary can serve as a benchmark for electricity load forecasting problems with new algorithms and datasets.

Li, Han↗